Agent skill

Fetch Linuxdo Post

by Castor6 in Castor6/tactus

获取 linux.do 帖子的正文及评论区内容,并解析评论回复关系。当需要获取L站帖子完整内容时使用此技能. An agent skill from Castor6/tactus.

Apache-2.0Auto-check passed

Install Fetch Linuxdo Post

skills CLI
$ npx skills add Castor6/tactus --skill fetch-linuxdo-post -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Castor6/tactus fetch-linuxdo-post --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Castor6/tactus.git skills-src && mkdir -p .claude/skills && cp -r skills-src/resources/tactus_skills/fetch-linuxdo-post .claude/skills/fetch-linuxdo-post && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
fetch-linuxdo-post
GitHub stars
376
Token cost
~871 tokens
SKILL.md length
134 words
Files
2 (incl. scripts)
Skills in repo
2
Repo updated
First seen
Licence
Apache-2.0

At a glance

获取 linux.do 帖子的正文及评论区内容,并解析评论回复关系。当需要获取L站帖子完整内容时使用此技能. An agent skill from Castor6/tactus.

  • Works in 3 steps: 原始信息分析 → 话题聚类 (核心逻辑) → 生成摘要报告
  • SKILL.md covers 使用说明 and linux.do 网站帖子总结专用提示词
  • Runs JavaScript scripts from its folder

What it does

Fetch Linuxdo Post is an agent skill from Castor6/tactus. 获取 linux.do 帖子的正文及评论区内容,并解析评论回复关系。当需要获取L站帖子完整内容时使用此技能。

Its SKILL.md is about 870 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/fetch-post.js`).

It works with Linux and Chrome Extensions. The repository describes itself as: The first browser AI Agent extension to support Agent Skills, enabling AI to perform complex tasks through an expandable skill system. 🌟 Star if you like it! | 首个支持 Agent Skills…. The licence is Apache-2.0.

Example prompts

  • “/fetch-linuxdo-post”

Requirements

  • Node.js
  • Docker

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. 原始信息分析
  2. 话题聚类 (核心逻辑)
  3. 生成摘要报告

What it can do on your machine

Read from SKILL.md and the folder at commit b055cef. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (JavaScript), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Fetch Linuxdo Post loads about 871 tokens when it runs. Until then it costs about 18 tokens; SKILL.md has 134 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~18
When it runs · the whole SKILL.md, loaded when a task matches
~871

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from Castor6/tactus at commit b055cef, republished under its Apache-2.0 licence (© Castor6). 134 words, ~871 tokens.

Download SKILL.mdSave it as .claude/skills/fetch-linuxdo-post/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
fetch-linuxdo-post
description
获取 linux.do 帖子的正文及评论区内容,并解析评论回复关系。当需要获取L站帖子完整内容时使用此技能。

使用说明

通过 API 请求获取 linux.do 论坛帖子的正文和评论区内容,支持解析评论之间的回复关系。

前置条件

脚本需要在 linux.do 页面上执行,浏览器会自动携带用户的登录 cookie。

脚本参数

通过 arguments 传入,脚本中通过 __args__ 获取:

参数类型必填说明
topicIdnumber/string是帖子 ID
调用示例
json
{ 
  "skill_name": "fetch-linuxdo-post", 
  "script_path": "scripts/fetch-post.js",
  "arguments": { "topicId": 12345 }
}
返回值

返回值有两种模式,取决于 JSON API 是否可用:

模式一:threads(讨论串模式,JSON API 正常)
json
{
  "success": true,
  "mode": "threads",
  "topic": {
    "id": 12345,
    "title": "帖子标题"
  },
  "mainPost": {
    "author": "作者名",
    "content": "帖子正文内容",
    "createdAt": "2026-01-15 16:14:29"
  },
  "threads": [
    [
      {
        "postNumber": 2,
        "author": "评论者",
        "content": "评论内容",
        "createdAt": "2026-01-15 16:14:55",
        "replyTo": 1
      },
      {
        "postNumber": 5,
        "author": "回复者",
        "content": "回复内容",
        "createdAt": "2026-01-15 16:15:30",
        "replyTo": 2
      }
    ]
  ],
  "totalPosts": 10,
  "threadsCount": 3,
  "message": "成功获取帖子内容,共 10 条帖子(含主帖),3 个讨论串"
}
模式二:comments(原始评论模式,JSON API 异常时降级)
json
{
  "success": true,
  "mode": "comments",
  "topic": {
    "id": 12345,
    "title": null
  },
  "mainPost": {
    "author": "作者名",
    "content": "帖子正文内容",
    "createdAt": "2026-01-15 16:14:29"
  },
  "comments": [
    {
      "postNumber": 2,
      "author": "评论者",
      "content": "评论内容",
      "createdAt": "2026-01-15 16:14:55"
    }
  ],
  "totalPosts": 10,
  "commentsCount": 9,
  "message": "成功获取帖子内容(降级模式),共 10 条帖子(含主帖),9 条评论"
}
数据结构说明
  • mode: 返回模式,threads 或 comments
  • mainPost: 帖子正文(1楼)
  • threads: 讨论串数组,每个讨论串是按楼层排序的评论数组(仅 threads 模式)
  • comments: 原始评论列表,按楼层排序(仅 comments 模式)
  • replyTo: 回复的目标楼层(仅 threads 模式有此字段)
使用流程
  1. 激活此 skill
  2. 传入帖子 ID 执行 scripts/fetch-post.js
  3. 获取结构化的帖子内容和评论数据
  4. 可用于后续的内容总结、分析等操作

linux.do 网站帖子总结专用提示词

当需要总结linux.do 网站帖子时,使用以下的提示词:

Role

你是一名资深的 Tech 社区内容策展人,专注于 linux.do 极客社区的深度总结。你擅长从海量的灌水讨论中提取高价值的技术细节、观点交锋和解决方案。你的目标是为用户提供一份“读后即懂”的社区精华情报。

Goals
  1. 主帖解构:精准概括楼主的核心意图与资源/技术要点。
  2. 讨论聚类:将评论区碎片化的回复按“话题维度”重组,而非按时间线罗列。
  3. 降噪处理:完全忽略“前排”、“Mark”、“顶”、“不明觉厉”等无信息增量的客套话。
  4. 贡献溯源:在引用重要观点或补充方案时,必须显式提及提出该观点的用户名(佬友)。
Workflow

请按照以下步骤处理输入的内容:

Step 1: 原始信息分析
  • 识别楼主(OP)及其核心内容。
  • 扫描评论区,标记出含有以下特征的回复:
    • 提出了具体的替代方案或优化建议。
    • 指出了潜在 Bug、安全风险或法律风险。
    • 进行了实质性的技术探讨或哲学反思。
    • 楼主(OP)亲自回复并表示认可的内容。
Step 2: 话题聚类 (核心逻辑)

将筛选出的高质量回复归类到相关的 Topic 下。例如:

  • Topic A: 技术可行性与 Bug 修复
  • Topic B: 替代方案竞品对比
  • Topic C: 安全与隐私担忧
Step 3: 生成摘要报告

输出一份 Markdown 格式的报告,语气专业、客观且带有社区亲和力。

Output Format (Markdown)
md
## ⚡️ 前排省流 (by @楼主ID)
> [一句话总结这个帖子是做什么的,例如:发布了一个基于 o1 模型的开源代码审计工具]

- **核心价值**:[列出 1-3 个关键点,如功能亮点、解决的痛点]
- **资源/指引**:[提取关键链接、指令或下载方式,如有]

## 💡 佬友精选讨论
*(注意:请根据实际讨论内容动态生成以下子标题,不要生硬套用。如果没有相关讨论则不显示)*

**1. [话题一:例如 关于部署难度的讨论]**
- **@用户A** 指出 Docker 部署存在权限问题,建议使用 `[具体方案]`。
- **@用户B** 补充了 Windows 环境下的配置参数。

**2. [话题二:例如 竞品对比]**
- **@用户C** 认为该工具比 Cursor 更轻量,但缺少 `[具体功能]`。
- **@用户D** 推荐了同类的开源项目 `[项目名]` 作为替代。

**3. [话题三:例如 安全/合规提醒]**
- **@用户E** 提醒该脚本可能会导致封号风险,建议仅在测试环境使用。

## 🚀 总结与共识
- **社区风向**:[推荐尝试 / 观望 / 存在争议 / 仅供娱乐]
- **最佳实践**:[如果评论区有公认的最佳解决方案或避坑指南,在这里总结]
Constraints
  • 必须保留原本的技术术语,不要过度翻译。
  • 对评论者的引用格式统一为 @用户名。
  • 如果评论区全是灌水,请直接在“佬友精选讨论”部分注明“暂无实质性讨论”。
  • 保持输出的紧凑性,便于在浏览器侧边栏阅读。

© Castor6, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (scripts) in resources/tactus_skills/fetch-linuxdo-post of Castor6/tactus.

  • SKILL.md
  • scripts/fetch-post.js

Open the folder on GitHubat commit b055cef

Compare with similar skills

Fetch Linuxdo Post next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Fetch Linuxdo Post compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Fetch Linuxdo Post this skillCastor6/tactus376—~871Automated safety check: PassApache-2.0
Vellum Client Capabilitiesvellum-ai/vellum-assistant1.4k—~1.2kAutomated safety check: PassMIT
Configuring Horizoncoollabsio/coolify63k4 repos~898Automated safety check: PassMIT
Canvas Capture Extensionremotion-dev/remotion62k—~868Automated safety check: PassCustom licence
K8s Security PoliciesCybereason-Public/owLSM28011 repos~2kAutomated safety check: PassGPL-2.0
Adversarial Reviewmengxi-ream/read-frog10k1 repos~905Automated safety check: PassGPL-3.0

Similar skills

  • Vellum Client Capabilities

    vellum-ai/vellum-assistant

    Truthful answers about what the Vellum client apps can and cannot do on the user's device.

    1.4k GitHub stars~1.2k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed
  • Configuring Horizon

    coollabsio/coolify

    A skill your agent uses whenever the user mentions Horizon by name in a Laravel context.

    63k GitHub starsUsed in 4 repos~898 tokens
    Backend & APIsAuto-check passed
  • Canvas Capture Extension

    remotion-dev/remotion

    Official

    Rebuild, install, and reload the private Remotion Canvas Capture unpacked Chrome extension.

    62k GitHub stars~868 tokensUpdated today
    Media & CreativeAuto-check passed
  • K8s Security Policies

    Cybereason-Public/owLSM

    Comprehensive guide for implementing NetworkPolicy, PodSecurityPolicy, RBAC, and Pod Security Standards in Kubernetes.

    280 GitHub starsUsed in 11 repos~2k tokens
    Backend & APIsAuto-check passed
  • Adversarial Review

    mengxi-ream/read-frog

    Adversarial code review using cross-model approach. An agent skill from mengxi-ream/read-frog.

    10k GitHub starsUsed in 1 repo~905 tokens
    DevelopmentAuto-check passed
  • Record Extension Demo

    mengxi-ream/read-frog

    Record polished, evidence-backed demos of the Read Frog extension as MP4 (and optional GIF) by driving real Chrome with the built extension, following captioned scene scripts, asserting extension…

    10k GitHub stars~2.8k tokensUpdated today
    DevelopmentAuto-check passed

More from Castor6/tactus

  • Design Style

    Castor6/tactus

    A skill your agent uses whenever the user asks to build, create, design, develop, improve, or style any frontend interface or visual element.

    376 GitHub starsUsed in 1 repo~2.1k tokens
    Auto-check passed

Questions about Fetch Linuxdo Post

What does Fetch Linuxdo Post do?

获取 linux.do 帖子的正文及评论区内容,并解析评论回复关系。当需要获取L站帖子完整内容时使用此技能. An agent skill from Castor6/tactus. Fetch Linuxdo Post is an agent skill from Castor6/tactus.

How do I install Fetch Linuxdo Post in Claude Code?

Run `npx skills add Castor6/tactus --skill fetch-linuxdo-post -a claude-code`. Or copy the skill folder (resources/tactus_skills/fetch-linuxdo-post in Castor6/tactus) into .claude/skills/fetch-linuxdo-post in your project. Claude Code loads it when a task matches its description.

How do I install Fetch Linuxdo Post in Codex?

Run `npx skills add Castor6/tactus --skill fetch-linuxdo-post -a codex`. Or copy the skill folder (resources/tactus_skills/fetch-linuxdo-post in Castor6/tactus) into .agents/skills/fetch-linuxdo-post in your project. Codex loads it when a task matches its description.

Can I use Fetch Linuxdo Post in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Castor6/tactus --skill fetch-linuxdo-post -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/fetch-linuxdo-post, .gemini/skills/fetch-linuxdo-post, .github/skills/fetch-linuxdo-post and .opencode/skills/fetch-linuxdo-post in your project.

What does Fetch Linuxdo Post need to run?

Going by SKILL.md and its folder, Fetch Linuxdo Post needs JavaScript for the scripts in its folder. Our summary lists: Node.js; Docker.

Does Fetch Linuxdo Post access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Fetch Linuxdo Post safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Fetch Linuxdo Post use?

Fetch Linuxdo Post is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Fetch Linuxdo Post use?

About 871 tokens (SKILL.md is roughly 3.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Fetch Linuxdo Post?

Skills that share tags, products or a category with Fetch Linuxdo Post: Vellum Client Capabilities (vellum-ai/vellum-assistant, 1.4k stars), Configuring Horizon (coollabsio/coolify, 63k stars), Canvas Capture Extension (remotion-dev/remotion, 62k stars) and K8s Security Policies (Cybereason-Public/owLSM, 280 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Fetch Linuxdo Post?

Castor6 (a GitHub user) maintains it in Castor6/tactus, which has 376 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on May 10, 2026.

Source: Castor6/tactus on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.